Using Transformer-based Neural Networks for classifying cellular states in Glioblastoma
| dc.contributor.author | Hedberg, Ronja | |
| dc.contributor.department | Chalmers tekniska högskola / Institutionen för matematiska vetenskaper | sv |
| dc.contributor.examiner | Jörnsten, Rebecka | |
| dc.contributor.supervisor | Jörnsten, Rebecka | |
| dc.contributor.supervisor | Lozada Cortés, Alejandro | |
| dc.date.accessioned | 2025-01-14T09:36:31Z | |
| dc.date.available | 2025-01-14T09:36:31Z | |
| dc.date.issued | 2024 | |
| dc.date.submitted | ||
| dc.description.abstract | By taking inspiration from the progress made in Natural Language Processing with the use of Transformer-based Neural Networks, similar approaches have been proposed for single-cell RNA-sequencing data in hope of capturing complex gene-to-gene interactions. One such approach is the pre-trained single-cell bidirectional encoder (scBERT), whose architecture and pre-training follows its Natural Language counterpart, BERT. Unlike BERT, scBERT was pre-trained for masked gene expression prediction using single-cell datasets comprising over 1.5 million single-cell RNAsequencing profiles. This thesis performs an initial assessment of the use of scBERT with novel single-cell data. In classifying annotated cellular states of Glioblastoma, the inclusion of scBERT showed overall limited advantages compared to using the gene expression directly. However, through the simulation of different scenarios, this thesis provides preliminary evidence in favor of the use of scBERT in the lack of ample signal (low number of expressed genes, and scarce number of training examples). This showcases the potential benefits of using the gene representations of massive single-cell Transformer-based models, especially when little information is available, which is frequently the case when working with in-house data or heavily underrepresented cellular states. | |
| dc.identifier.coursecode | MVEX60 | |
| dc.identifier.uri | http://hdl.handle.net/20.500.12380/309083 | |
| dc.language.iso | eng | |
| dc.setspec.uppsok | PhysicsChemistryMaths | |
| dc.subject | Machine Learning, scRNA-seq, Transformer, Cellular states, Glioblastoma, Cancer, Natural Language Processing, Encoder. | |
| dc.title | Using Transformer-based Neural Networks for classifying cellular states in Glioblastoma | |
| dc.type.degree | Examensarbete för masterexamen | sv |
| dc.type.degree | Master's Thesis | en |
| dc.type.uppsok | H | |
| local.programme | Complex adaptive systems (MPCAS), MSc |